Welcome To The Algorithm Page of Sigma70Pred


Sigma70Pred is a web-server with the capability of identifying σ70 promoters. Bacterial DNA contains specific nucleotide sequences called promoters that can bind to RNA polymerase. Sigma70 or σ70 is one of the essential promoter sequences which is present in most of the DNA regulatory functions. Under normal conditions, it governs the transcription of most of the housekeeping genes.

The prediction server for σ70 promoter has been designed in a very user-friendly manner. Here, on this page, user can get the details of all the algorithms and procedures exploited in the different modules.



Datasets Used

Benchmark Dataset:

It comprises of 741 σ70 promoter sequences and 1400 non-promoter sequences.

Validation Dataset:

For the sake of checking the robustness of our model, we have taken the updated sequences from newest version of RegulonDB i.e. 10.8, as of February 2021. It comprises of 1134 σ70 promoter sequences and 638 non-promoter sequences.



This algorithm of the server is implemented on the following three modules:

Prediction module

The "Predict" module provides the facility to the user to classify σ70 promoters from the non-promoter sequences. User can provide multiple sequences as input to the server to predict the given sequence as σ70 promoter/non-promoter.In this study we used Support Vector Classifier to develop prediction modules.

Scan module

The "Scan" module provides the facility to the user to classify σ70 promoters from the non-promoter sequences, by generating the patterns of length 81 from the submitted sequence. User can provide only one sequence as input to the server to generate and predict the given sequence as σ70 promoter/non-promoter.In this study we used Support Vector Classifier to develop prediction modules.

Design module

The "Design" module provides the facility to the user to classify σ70 promoters from the non-promoter sequences, by generating all the possible mutants of the submitted sequence. User can provide only one sequence as input to the server to generate and predict the given sequence as σ70 promoter/non-promoter.In this study we used Support Vector Classifier to develop prediction modules.